96 citations · 227 across the 20 of their papers we have counts for
21 papers
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Youquan Liu, Runnan Chen, Xin Li +9
Point-, voxel-, and range-views are three representative forms of point clouds. All of them have accurate 3D measurements but lack color and texture information. RGB images are a n…
Human-centric Scene Understanding for 3D Large-scale Scenarios
Yiteng Xu, Peishan Cong, Yichen Yao +6
Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human…
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Yuhang Lu, Qi Jiang, Runnan Chen +3
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipel…
Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID
Xulin Li, Yan Lu, Bin Liu +6
In cloth-changing person re-identification (CCReID), it is critical to learn clothes-invariant feature, which can provide discriminative ID features that remain robust against clot…
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
Zhenxiang Lin, Xidong Peng, Peishan Cong +6
We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images…
LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
Xin Li, Tao Ma, Yuenan Hou +8
LiDAR-camera fusion methods have shown impressive performance in 3D object detection. Recent advanced multi-modal methods mainly perform global fusion, where image features and poi…
SCPNet: Semantic Scene Completion on Point Cloud
Zhaoyang Xia, Youquan Liu, Xin Li +5
Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inheren…
Rethinking Range View Representation for LiDAR Segmentation
Lingdong Kong, Youquan Liu, Runnan Chen +6
LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point- or voxel-based methods as they often yield better performance than the traditional range…
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
Runnan Chen, Youquan Liu, Lingdong Kong +6
Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the…
EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder
Xiaoshui Huang, Zhou Huang, Sheng Li +5
The pretrain-finetune paradigm has achieved great success in NLP and 2D image fields because of the high-quality representation ability and transferability of their pretrained mode…
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
Xin Li, Botian Shi, Yuenan Hou +4
Multi-modal 3D object detection has been an active research topic in autonomous driving. Nevertheless, it is non-trivial to explore the cross-modal feature fusion between sparse 3D…
Mind the Gap in Distilling StyleGANs
Guodong Xu, Yuenan Hou, Ziwei Liu +1
StyleGAN family is one of the most popular Generative Adversarial Networks (GANs) for unconditional generation. Despite its impressive performance, its high demand on storage and c…
Vision-Centric BEV Perception: A Survey
Yuexin Ma, Tai Wang, Xuyang Bai +7
In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing…
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
Yuenan Hou, Xinge Zhu, Yuexin Ma +2
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distill…
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
Peishan Cong, Xinge Zhu, Feng Qiao +7
Accurately detecting and tracking pedestrians in 3D space is challenging due to large variations in rotations, poses and scales. The situation becomes even worse for dense crowds w…
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image Classification
Xiaohan Xing, Yuenan Hou, Hang Li +3
The amount of medical images for training deep classification models is typically very scarce, making these deep models prone to overfit the training data. Studies showed that know…
Network Pruning via Resource Reallocation
Yuenan Hou, Zheng Ma, Chunxiao Liu +2
Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network. Contemporar…
Inter-Region Affinity Distillation for Road Marking Segmentation
Yuenan Hou, Zheng Ma, Chunxiao Liu +2
We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation. In this work, we explore…
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Yuenan Hou, Zheng Ma, Chunxiao Liu +1
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context…
Agnostic Lane Detection
Yuenan Hou
Lane detection is an important yet challenging task in autonomous driving, which is affected by many factors, e.g., light conditions, occlusions caused by other vehicles, irrelevan…
Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
Yuenan Hou, Zheng Ma, Chunxiao Liu +1
The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, t…